paper-analyzer

Convert academic PDF papers into Markdown or HTML technical articles.

1|Updated Feb 27, 2026

Search Tags:#markdown #html #content generation #academic paper #miner u #pdf analysis

Ready to run

npx skills add https://github.com/gatieme/agent-toolkit --skill paper-analyzer-gatieme

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: paper-analyzer
Source: https://github.com/gatieme/agent-toolkit/tree/main/skills/paper-analyzer
Command: npx skills add https://github.com/gatieme/agent-toolkit --skill paper-analyzer-gatieme

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, markdown, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the transformation of dense academic papers into engaging, well-structured technical articles, catering to various writing styles and technical depths.

Core Features & Use Cases

High-Precision PDF Parsing: Utilizes MinerU Cloud API to accurately extract text, images, tables, and LaTeX formulas from PDFs.
Style Customization: Supports 'storytelling', 'academic', and 'concise' writing styles.
Enhanced Content: Optionally includes detailed formula explanations and GitHub code analysis.
Output Formats: Generates both Markdown and HTML with embedded images.
Use Case: Convert a complex research paper on AI into a blog post for a general audience, or into a concise summary for a technical review.

Quick Start

Use the paper-analyzer skill to convert the PDF file 'research_paper.pdf' into a storytelling-style article.

Frequently Asked Questions about paper-analyzer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert an academic PDF paper into a readable Markdown article?▼

To convert an academic PDF paper into a Markdown article, this Skill uses the MinerU Cloud API to parse text, images, and LaTeX formulas, then reformats them into narrative or academic prose. It outputs polished Markdown and HTML files.

Can I extract LaTeX formulas and tables from a PDF for academic content generation?▼

Yes, you can extract LaTeX formulas and tables from a PDF for academic content generation. The Skill utilizes high-precision PDF parsing to pull these elements and optionally includes detailed formula explanations within the final output.

Does the paper-analyzer support transforming research papers into a storytelling style?▼

The paper-analyzer supports transforming research papers into a storytelling style. It offers style customization including storytelling, academic, and concise formats to tailor the technical depth for different audiences.

How does PDF parsing handle embedded images for HTML content generation?▼

PDF parsing handles embedded images for HTML content generation by extracting them via the MinerU Cloud API and embedding them directly into the final HTML output. This ensures visual elements are retained in the converted article.

What is the best way to summarize complex AI research papers for a blog post?▼

The best way to summarize complex AI research papers for a blog post is using automated transformation tools that parse dense PDFs and reformat the content into engaging, narrative prose. This Skill converts technical papers into accessible articles.